import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

df = pd.read_csv('Loan.csv')

df.isnull().sum()

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 20000 entries, 0 to 19999
Data columns (total 36 columns):
 #   Column                      Non-Null Count  Dtype  
---  ------                      --------------  -----  
 0   ApplicationDate             20000 non-null  object 
 1   Age                         20000 non-null  int64  
 2   AnnualIncome                20000 non-null  int64  
 3   CreditScore                 20000 non-null  int64  
 4   EmploymentStatus            20000 non-null  object 
 5   EducationLevel              20000 non-null  object 
 6   Experience                  20000 non-null  int64  
 7   LoanAmount                  20000 non-null  int64  
 8   LoanDuration                20000 non-null  int64  
 9   MaritalStatus               20000 non-null  object 
 10  NumberOfDependents          20000 non-null  int64  
 11  HomeOwnershipStatus         20000 non-null  object 
 12  MonthlyDebtPayments         20000 non-null  int64  
 13  CreditCardUtilizationRate   20000 non-null  float64
 14  NumberOfOpenCreditLines     20000 non-null  int64  
 15  NumberOfCreditInquiries     20000 non-null  int64  
 16  DebtToIncomeRatio           20000 non-null  float64
 17  BankruptcyHistory           20000 non-null  int64  
 18  LoanPurpose                 20000 non-null  object 
 19  PreviousLoanDefaults        20000 non-null  int64  
 20  PaymentHistory              20000 non-null  int64  
 21  LengthOfCreditHistory       20000 non-null  int64  
 22  SavingsAccountBalance       20000 non-null  int64  
 23  CheckingAccountBalance      20000 non-null  int64  
 24  TotalAssets                 20000 non-null  int64  
 25  TotalLiabilities            20000 non-null  int64  
 26  MonthlyIncome               20000 non-null  float64
 27  UtilityBillsPaymentHistory  20000 non-null  float64
 28  JobTenure                   20000 non-null  int64  
 29  NetWorth                    20000 non-null  int64  
 30  BaseInterestRate            20000 non-null  float64
 31  InterestRate                20000 non-null  float64
 32  MonthlyLoanPayment          20000 non-null  float64
 33  TotalDebtToIncomeRatio      20000 non-null  float64
 34  LoanApproved                20000 non-null  int64  
 35  RiskScore                   20000 non-null  float64
dtypes: float64(9), int64(21), object(6)
memory usage: 5.5+ MB

df['LoanApproved'] = df['LoanApproved'].map({1: 'Approved', 0: 'Not Approved'})

# Select numeric columns
numeric_cols = df.select_dtypes(include=['int64', 'float64']).columns

# Calculate the correlation matrix for numeric columns
corr_matrix = df[numeric_cols].corr()

# Plot the heatmap
plt.figure(figsize=(10, 8))
sns.heatmap(corr_matrix, cmap='coolwarm', square=True)
plt.title('Correlation Matrix')
plt.show()

df['EmploymentStatus'].value_counts().plot(kind = 'pie', autopct = '%.2f%%')

<Axes: ylabel='count'>

df['LoanApproved'].value_counts().plot(kind = 'pie', autopct = '%.2f%%')

<Axes: ylabel='count'>

df['EducationLevel'].value_counts().plot(kind = 'pie', autopct = '%.2f%%')

<Axes: ylabel='count'>

df['LoanPurpose'].value_counts().plot(kind = 'pie', autopct = '%.2f%%')

<Axes: ylabel='count'>

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='Age', y='LoanAmount', hue='LoanApproved', alpha=0.7)
plt.title('Age vs Loan Amount')
plt.xlabel('Age')
plt.ylabel('Loan Amount')
plt.legend(title='Loan Approved')
plt.show()

plt.figure(figsize=(8, 5))
sns.violinplot(data=df, x='EducationLevel', y='AnnualIncome', palette='muted', split=True, hue='LoanPurpose')
plt.title('Annual Income by Education')
plt.xlabel('Education Level')
plt.ylabel('Annual Income')
plt.show()

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='AnnualIncome', y='CreditScore', hue='LoanApproved', alpha=0.7, palette='coolwarm')
plt.title('Annual Income vs Credit Score')
plt.xlabel('Annual Income')
plt.ylabel('Credit Score')
plt.legend(title='Loan Approved')
plt.show()

plt.figure(figsize=(8, 5))
sns.countplot(data=df, x='EmploymentStatus', hue='LoanApproved', palette='viridis')
plt.title('Loan Approval by Employment Status')
plt.xlabel('Employment Status')
plt.ylabel('Count')
plt.legend(title='Loan Approved')
plt.show()

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='CreditScore', y='RiskScore', alpha=0.6, hue='LoanApproved', palette='coolwarm')
plt.title('Credit Score vs Risk Score')
plt.xlabel('Credit Score')
plt.ylabel('Risk Score')
plt.legend(title='Loan Approved')
plt.show()

plt.figure(figsize=(8, 5))
sns.boxplot(data=df, x='MaritalStatus', y='LoanAmount', hue='LoanApproved', palette='pastel')
plt.title('Loan Amount by Marital Status')
plt.xlabel('Marital Status')
plt.ylabel('Loan Amount')
plt.legend(title='Loan Approved')
plt.show()

plt.figure(figsize=(8, 5))
sns.boxplot(data=df, x='LoanPurpose', y='LoanAmount')
plt.title('Loan Amount by Loan Purpose')
plt.xlabel('Loan Purpose')
plt.ylabel('Loan Amount')
plt.show()

plt.figure(figsize=(8, 5))
sns.boxplot(data=df, x='LoanApproved', y='SavingsAccountBalance')
plt.title('Savings Account Balance by Loan Approval')
plt.xlabel('Loan Approved')
plt.ylabel('Savings Account Balance')
plt.show()

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='AnnualIncome', y='LoanAmount', hue='EducationLevel', alpha=0.7, palette='viridis')
plt.title('Annual Income vs Loan Amount by Education Level')
plt.xlabel('Annual Income')
plt.ylabel('Loan Amount')
plt.legend(title='Education Level')
plt.show()

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='DebtToIncomeRatio', y='CreditScore', hue='HomeOwnershipStatus', palette='coolwarm', alpha=0.6)
plt.title('Debt-to-Income Ratio vs Credit Score by Home Ownership Status')
plt.xlabel('Debt-to-Income Ratio')
plt.ylabel('Credit Score')
plt.legend(title='Home Ownership Status')
plt.show()

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='MonthlyIncome', y='LoanAmount', hue='MaritalStatus', alpha=0.7, palette='pastel')
plt.title('Monthly Income vs Loan Amount by Marital Status')
plt.xlabel('Monthly Income')
plt.ylabel('Loan Amount')
plt.legend(title='Marital Status')
plt.show()

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='CreditCardUtilizationRate', y='CreditScore', alpha=0.7, hue='EducationLevel', palette='muted')
plt.title('Credit Card Utilization Rate vs Credit Score by Education Level')
plt.xlabel('Credit Card Utilization Rate')
plt.ylabel('Credit Score')
plt.legend(title='Education Level')
plt.show()

plt.figure(figsize=(8, 5))
sns.boxplot(data=df, x='BankruptcyHistory', y='NetWorth')
plt.title('Net Worth by Bankruptcy History')
plt.xlabel('Bankruptcy History (Yes=1, No=0)')
plt.ylabel('Net Worth')
plt.show()

plt.figure(figsize=(8, 5))
sns.heatmap(df[['RiskScore', 'CreditScore']].corr(), annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5)
plt.title('Correlation between Risk Score and Credit Score')
plt.show()

loan_avg = df.pivot_table(values='LoanAmount', index='MaritalStatus', columns='EmploymentStatus', aggfunc='mean')
plt.figure(figsize=(10, 6))
sns.heatmap(loan_avg, annot=True, fmt=".1f", cmap="YlGnBu", linewidths=0.5)
plt.title('Average Loan Amount by Marital Status and Employment Status')
plt.xlabel('Employment Status')
plt.ylabel('Marital Status')
plt.show()

plt.figure(figsize=(10, 6))
pivot_table = df.pivot_table(index='EmploymentStatus', columns='HomeOwnershipStatus', values='RiskScore', aggfunc='mean')
sns.heatmap(pivot_table, annot=True, fmt=".2f", cmap="coolwarm", linewidths=0.5)
plt.title('Risk Score by Employment Status and Homeownership Status')
plt.xlabel('Homeownership Status')
plt.ylabel('Employment Status')

Text(95.72222222222221, 0.5, 'Employment Status')

plt.figure(figsize=(10, 6))
pivot_table = df.pivot_table(index='EducationLevel', columns='HomeOwnershipStatus', values='TotalDebtToIncomeRatio', aggfunc='mean')
sns.heatmap(pivot_table, annot=True, fmt=".2f", cmap="coolwarm", linewidths=0.5)
plt.title('Risk Score by Employment Status and Homeownership Status')
plt.xlabel('Homeownership Status')
plt.ylabel('Employment Status')

Text(95.72222222222221, 0.5, 'Employment Status')

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='NetWorth', y='RiskScore', hue='LoanApproved', alpha=0.7, palette='coolwarm')
plt.title('Net Worth vs Risk Score')

Text(0.5, 1.0, 'Net Worth vs Risk Score')

plt.figure(figsize=(8, 5))
sns.barplot(data=df, x='LoanApproved', y='NetWorth')
plt.title('Net Worth by Loan Approval Status')
plt.xlabel('Loan Approved')

Text(0.5, 0, 'Loan Approved')

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='CreditCardUtilizationRate', y='RiskScore', hue='LoanApproved', alpha=0.7, palette='coolwarm')
plt.title('Credit Card Utilization Rate vs Risk Score')

Text(0.5, 1.0, 'Credit Card Utilization Rate vs Risk Score')

plt.figure(figsize=(8, 5))
sns.scatterplot(data=df, x='AnnualIncome', y='TotalLiabilities', hue='LoanApproved', alpha=0.7, palette='coolwarm')
plt.title('Annual Income vs Total Liabilities')
plt.xlabel('Annual Income')
plt.ylabel('Total Liabilities')
plt.legend(title='Loan Approved')
plt.show()

plt.figure(figsize=(10, 6))
sns.scatterplot(
    data=df,
    x='MonthlyLoanPayment',
    y='TotalDebtToIncomeRatio',
    hue='LoanApproved',  # Color based on Loan approved
    alpha=0.6
)

plt.title('Debt-to-Income Ratio vs. Monthly Loan Payment')
plt.xlabel('Monthly Loan Payment')
plt.ylabel('Debt-to-Income Ratio')
plt.legend(title='Loan approved')
plt.show()

plt.figure(figsize=(10, 6))
# Example: Pivot for risk score mean
mean_risk_score = df.pivot_table(
    index='BankruptcyHistory',
    columns='EmploymentStatus',
    values='RiskScore',
    aggfunc='mean'
)

df1 = df
df1['LoanApproved'] = df1['LoanApproved'].map({'Approved': 1, 'Not Approved': 0})

# Calculate loan approval percentage
loan_approval_pct = df1.groupby(['BankruptcyHistory', 'EmploymentStatus'])['LoanApproved'].mean().unstack() * 100

# Combine data for annotations
annot = mean_risk_score.copy()
for i in annot.index:
    for j in annot.columns:
        risk = mean_risk_score.loc[i, j]
        pct = loan_approval_pct.loc[i, j]
        annot.loc[i, j] = f"{risk:.2f}\n({pct:.1f}%)"

# Plotting the heatmap
plt.figure(figsize=(12, 8))
sns.heatmap(
    mean_risk_score,
    annot=annot,
    fmt="",
    cmap="coolwarm",
    linewidths=0.5,
    cbar_kws={'label': 'Mean Risk Score'}
)
plt.title('Risk Score and Loan Approval Percentage by Bankruptcy History and Employment Status')
plt.xlabel('EmploymentStatus')
plt.ylabel('BankruptcyHistory')
plt.show()

<ipython-input-128-043cef68047c>:22: FutureWarning: Setting an item of incompatible dtype is deprecated and will raise an error in a future version of pandas. Value '49.66
(24.7%)' has dtype incompatible with float64, please explicitly cast to a compatible dtype first.
  annot.loc[i, j] = f"{risk:.2f}\n({pct:.1f}%)"
<ipython-input-128-043cef68047c>:22: FutureWarning: Setting an item of incompatible dtype is deprecated and will raise an error in a future version of pandas. Value '51.84
(28.6%)' has dtype incompatible with float64, please explicitly cast to a compatible dtype first.
  annot.loc[i, j] = f"{risk:.2f}\n({pct:.1f}%)"
<ipython-input-128-043cef68047c>:22: FutureWarning: Setting an item of incompatible dtype is deprecated and will raise an error in a future version of pandas. Value '53.23
(18.6%)' has dtype incompatible with float64, please explicitly cast to a compatible dtype first.
  annot.loc[i, j] = f"{risk:.2f}\n({pct:.1f}%)"

<Figure size 1000x600 with 0 Axes>

	0
ApplicationDate	0
Age	0
AnnualIncome	0
CreditScore	0
EmploymentStatus	0
EducationLevel	0
Experience	0
LoanAmount	0
LoanDuration	0
MaritalStatus	0
NumberOfDependents	0
HomeOwnershipStatus	0
MonthlyDebtPayments	0
CreditCardUtilizationRate	0
NumberOfOpenCreditLines	0
NumberOfCreditInquiries	0
DebtToIncomeRatio	0
BankruptcyHistory	0
LoanPurpose	0
PreviousLoanDefaults	0
PaymentHistory	0
LengthOfCreditHistory	0
SavingsAccountBalance	0
CheckingAccountBalance	0
TotalAssets	0
TotalLiabilities	0
MonthlyIncome	0
UtilityBillsPaymentHistory	0
JobTenure	0
NetWorth	0
BaseInterestRate	0
InterestRate	0
MonthlyLoanPayment	0
TotalDebtToIncomeRatio	0
LoanApproved	0
RiskScore	0